© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110174
    Prev
    Next
    INDEX
    Explanations

    travel/tours

    np_max-act · gemini-2.0-flash

    The neuron fires on the imperative/“call-to-action” verbs (and their immediate context) that kick off each listed travel activity in a tour itinerary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to cultural or scenic experiences in travel descriptions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     首
    -0.07
    Jer
    -0.07
    even
    -0.07
     userID
    -0.06
    卡
    -0.06
     messenger
    -0.06
    	switch
    -0.06
    /il
    -0.06
     وهو
    -0.06
    	text
    -0.06
    POSITIVE LOGITS
    Receiver
    0.07
     án
    0.07
     Meanwhile
    0.06
     размещ
    0.06
    сии
    0.06
    _COM
    0.06
     prod
    0.06
     receiver
    0.06
    	app
    0.06
    _animation
    0.06
    Activations Density 0.018%

    No Known Activations